Hello! I am writing regarding my post on GitHub. Is there any known solution to Auto-embedding generation directly from SageMaker AI Inference Endpoint to TypeSense? Any help will be highly appreciated. Thank you in advance. BR, Mehti

Not at the moment. But we do support vLLM, so if they have an adapter for sagemaker then it might work

@Jason Bosco thanks for your quick response! Is there any documentation/examples of using vLLM for populating embeddings to TypeSense?

vllm provides open api compatible endpoints. Once you deploy vllm, you can then change the base URL that Typesense uses to your vllm server: https://typesense.org/docs/27.1/api/vector-search.html#using-openai-compatible-apis